Pratinav Seth

← Publications / Tabular Foundation Models & Distillation

Distilling Tabular Foundation Models for Structured Health Data

Aditya Tanna, Nassim Bouarour, Mohamed Bouadi, Vinay Kumar Sankarapu, Pratinav Seth

SD4H Workshop, ICML 2026 · Spotlight2026My role: Senior authorWorkshop
PDFarXiv
Distilling Tabular Foundation Models for Structured Health Data pipeline

Abstract

Tabular foundation models (TFMs) achieve strong performance on health datasets, but their inference cost and infrastructure requirements limit practical use. We study whether their predictive behavior can be transferred to lightweight tabular models through knowledge distillation. Since in-context TFMs condition on the training set at inference time, naive distillation can introduce context leakage; we address this with stratified out-of-fold teacher labeling. Across 19 healthcare datasets, 6 TFM teachers, 4 student families, and several multi-teacher ensembles, we find that distilled students retain at least 90% of teacher AUC, outperforming teachers in some cases, while running at least 26× faster on CPU and preserving calibration and fairness critical for health applications. Moreover, multi-teacher averaging does not consistently improve over the best single teacher. Leakage-aware distillation is thus a viable route for bringing TFM-quality predictions into inference-constrained health settings.

Best Paper Runner-Up (Spotlight)

Cite

@inproceedings{tanna2026distilling,
  title         = {{Distilling Tabular Foundation Models for Structured Health Data}},
  author        = {Aditya Tanna and Nassim Bouarour and Mohamed Bouadi and Vinay Kumar Sankarapu and Pratinav Seth},
  booktitle     = {SD4H Workshop, ICML 2026 · Spotlight},
  year          = {2026},
  eprint        = {2605.18702},
  archivePrefix = {arXiv},
  url           = {https://arxiv.org/abs/2605.18702}
}
All →